The parameters of resistance wall, which is a novel flash structure for forging die, are studied. The effects of the resistance walls parameters are analyzed and the important influence factors are screened by using the fractional factorial design. The Latin hypercube method is used to select sample points of the important design variables which are analyzed by finite elements simulation. The surrogate models are established by taking the simulation result as response and the parameters of the resistance wall structure as variables. The model is converted into single objective function by linear weighting method and is optimized by using particle swarm optimization algorithm for global optimization. Finally，the optimization results are compared and verified with those obtained by genetic algorithm. The results show that the PSO (particle swarm optimization) algorithm has better convergence than the traditional genetic algorithm and can realize optimization of the parameters of the resistance wall structure.